Debiasing Word Embeddings

This file includes

1. A re-implementation of hard-debiasing algorithm developed by the paper: Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings by Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. Proceedings of NIPS 2016.
   Original code and data can be found on: https://github.com/tolga-b/debiaswe.

2. Debiasing results using conceptor negation. Conceptor is found by using gender specific words.

Results includes direct bias(gender direction) results and indirect bias(non-gender direction but showing gender bias) results.